Open Access
Translator Disclaimer
2014 The Construction and Approximation of the Neural Network with Two Weights
Zhiyong Quan, Zhengqiu Zhang
J. Appl. Math. 2014: 1-6 (2014). DOI: 10.1155/2014/892653

Abstract

The technique of approximate partition of unity, the way of Fourier series, and inequality technique are used to construct a neural network with two weights and with sigmoidal functions. Furthermore by using inequality technique, we prove that the neural network with two weights can more precisely approximate any nonlinear continuous function than BP neural network constructed in (Chen et al., 2012).

Citation

Download Citation

Zhiyong Quan. Zhengqiu Zhang. "The Construction and Approximation of the Neural Network with Two Weights." J. Appl. Math. 2014 1 - 6, 2014. https://doi.org/10.1155/2014/892653

Information

Published: 2014
First available in Project Euclid: 1 October 2014

zbMATH: 07131949
MathSciNet: MR3251593
Digital Object Identifier: 10.1155/2014/892653

Rights: Copyright © 2014 Hindawi

JOURNAL ARTICLE
6 PAGES


SHARE
Vol.2014 • 2014
Back to Top